© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23983
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person by the name of 'Bercow'

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of a specific character sequence related to "erc" and "roc" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hulk
    -0.78
     Gins
    -0.76
     Cyrus
    -0.69
     Maker
    -0.68
     Samoa
    -0.67
    ħĭ
    -0.66
     Twain
    -0.66
    MENTS
    -0.66
     Sanford
    -0.66
     Foley
    -0.65
    POSITIVE LOGITS
    kefeller
    1.27
    abulary
    1.24
    zyk
    1.17
    ourse
    1.10
    ourses
    1.07
    ombat
    1.06
    ounter
    1.04
    ussions
    1.03
    ounters
    1.02
    ursor
    1.00
    Activations Density 0.024%

    No Known Activations